Please wait a minute...
Big Data Mining and Analytics  2021, Vol. 4 Issue (1): 56-64    DOI: 10.26599/BDMA.2020.9020027
Special Issue on Intelligent Recommendation System and Big Data Analysis     
Multivariate Deep Learning Approach for Electric Vehicle Speed Forecasting
Youssef Nait Malek*(),Mehdi Najib(),Mohamed Bakhouya(),Mohammed Essaaidi()
LERMA Lab, College of Engineering and Architecture, International University of Rabat, Sala Al Jadida 11100, Morocco.
TICLab, College of Engineering and Architecture, International University of Rabat, Sala Al Jadida 11100, Morocco.
LERMA Lab, College of Engineering, International University of Rabat, Sala Al Jadida 11100, Morocco.
ENSIAS, Mohamed V University, Agdal Rabat 10112, Morocco.
Download: PDF (7075 KB)      HTML  
Export: BibTeX | EndNote (RIS)      

Abstract  

Speed forecasting has numerous applications in intelligent transport systems’ design and control, especially for safety and road efficiency applications. In the field of electromobility, it represents the most dynamic parameter for efficient online in-vehicle energy management. However, vehicles’ speed forecasting is a challenging task, because its estimation is closely related to various features, which can be classified into two categories, endogenous and exogenous features. Endogenous features represent electric vehicles’ characteristics, whereas exogenous ones represent its surrounding context, such as traffic, weather, and road conditions. In this paper, a speed forecasting method based on the Long Short-Term Memory (LSTM) is introduced. The LSTM model training is performed upon a dataset collected from a traffic simulator based on real-world data representing urban itineraries. The proposed models are generated for univariate and multivariate scenarios and are assessed in terms of accuracy for speed forecasting. Simulation results show that the multivariate model outperforms the univariate model for short- and long-term forecasting.



Key wordsElectric Vehicle (EV)      multivariate Long Short-Term Memory (LSTM)      speed forecasting      deep learning     
Received: 01 September 2020      Published: 12 January 2021
Fund:  collaborative framework OpenLab "PSA@Morocco - Sustainable mobility for Africa", and partially supported by MIGRID project(5-398, 2017-2019)
Corresponding Authors: Youssef Nait Malek     E-mail: youssef.nait-malek@uir.ac.ma;mehdi.najib@uir.ac.ma;mohamed.bakhouya@uir.ac.ma;essaaidi@ieee.org
About author: Youssef Nait Malek received the MS degree in networking and embedded systems from Molay Ismail University, Meknes, Morocco in 2017. Currently he is a PhD student at the Ecole Nationale Supérieure d’ Informatique et d’ Analyse des Systémes (ENSIAS), Mohamed V University. He joined the International University of Rabat in 2017 where he works on the Self-Serv Project as an internship, the project aimed to develop a platform for smarter health organization. He also helped develop a monitoring platform used in MIGRID and CASANET projects. He is currently developing predictive algorithms for speed forecasting and driving range in electric vehicles using machine learning methods, under the HELECAR project, which aims to develop approaches for optimal predictive energy management for Battery Electric Vehicles (BEV) and Plug-in Hybrid Electric Vehicles (PHEV) by using Moroccan Information and Communication Technologies (ICT). His research interests include IoT, big data technologies, and machine learning, as well as their applications.|Mehdi Najib received the PhD degree in computer science from the University of Le Havre in 2014. He is currently an assistant professor in computer science at International University of Rabat. He has published more than 20 papers in international conferences, journals, and books. He participated many research projects, such as Passage Portuaire for the risk management related to containers transportation and the Holsys project. His main research interests include forecasting, smart-building, and adaptive systems for workflow management, decision support system, and simulation and risk management.|Mohamed Bakhouya received the PhD degree from UTBM, France in 2005 and the Habilitation á Diriger des Researches (HDR) from Université de Technologie de Belfort Montbéliard (UTBM), France in 2013. He has more than ten years experience in participating and working in sponsored ICT projects. He is currently a professor in computer science at International University of Rabat. He was the editor-in-chief of IJARAS and also serves as a guest editor of a number of international journals, e.g., ACM Trans. on Autonomous and Adaptive Systems, Product Development Journal, Concurrency and Computation: Practice and Experience, FGCS, and MICRO. He has published more than 100 papers in international journals, books, and conferences. His research interests include various aspects related to the design, validation, and implementation of distributed and adaptive systems, architectures, and protocols.|Mohammed Essaaidi received the "Doctorat de Troisième Cycle" degree and the "Doctorat d’Etat" degree in electrical engineering with honors from Abdelmalek Essaadi University in Tetuan, Morocco in 1992 and 1997, respectively. He is a professor and former dean of ENSIAS, Mohammed V University, Morocco. He is a senior member of IEEE, the founder and past chairman of the IEEE Morocco section (2005-2015), the co-chair of IEEE IoT Smart Cities Summit, and the chair of MEA IEEE IoT Global Cities Alliance. He has authored/co-authored 10 books and more than 200 papers in international refereed journals and conferences in the field of electrical and computer engineering and their applications in areas, such as smart homes, smart mobility, smart grid, and smart cities. He is also an active member of the editorial boards of several international journals in the same fields mentioned above. His research interests focus mainly on RF and microwave passive and active circuits and antennas for wireless communications and medical systems.
Cite this article:

Youssef Nait Malek,Mehdi Najib,Mohamed Bakhouya,Mohammed Essaaidi. Multivariate Deep Learning Approach for Electric Vehicle Speed Forecasting. Big Data Mining and Analytics, 2021, 4(1): 56-64.

URL:

http://bigdata.tsinghuajournals.com/10.26599/BDMA.2020.9020027     OR     http://bigdata.tsinghuajournals.com/Y2021/V4/I1/56

Fig. 1 LSTM gate.
Fig. 2 Three itineraries used in the simulation.
Fig. 3 EV speed forecasting results for the univariate LSTM model, (a) one step, (b) 60 steps, and (c) 120 steps.
Fig. 4 EV speed forecasting results for the multivariate LSTM model, (a) one step, (b) 60 steps, and (c) 120 steps.
Training typeForecast horizon
1 step60 steps120 steps
Multivariate0.4540.6150.633
Univariate1.0335.4277.184
Table 1 RMSE error. (%)
Training typeForecast horizon
1 step60 steps120 steps
Multivariate1.221.451.63
Univariate3.9417.1421.68
Table 2 SMAPE error. (%)
[1]   Vaz W., Nandi A. K., Landers R. G., and Koylu U. O., Electric vehicle range prediction for constant speed trip using multi-objective optimization, Journal of Power Sources, vol. 275, pp. 435-446, 2015.
[2]   Li L., Coskun S., Zhang F., Langari R., and Xi J., Energy management of hybrid electric vehicle using vehicle lateral dynamic in velocity prediction, IEEE Transactions on Vehicular Technology, vol. 68, no. 4, pp. 3279-3293, 2019.
[3]   Stroe N., Colin G., Ben-Cherif K., Olaru S., and Chamaillard Y., Towards a generic control-oriented model for HEV predictive energy management, IFAC-PapersOnLine, vol. 49, no. 11, pp. 259-264, 2016.
[4]   Debert M., Yhamaillard G., and Ketfi-herifellicaud G. A., Predictive energy management for hybrid electric vehicles-prediction horizon and battery capacity sensitivity, IFAC Proceedings, vol. 43, no. 7, pp. 270-275, 2010.
[5]   Rezaei A. and Burl J. B., Prediction of vehicle velocity for model predictive control, IFAC-PapersOnLine, vol. 48, no. 15, pp. 257-262, 2015.
[6]   Cheng Z., Chow M. Y., Jung D., and Jeon J., A big data based deep learning approach for vehicle speed prediction, in Proc. 26th IEEE International Symposium on Industrial Electronics, Scotland, UK, 2017, pp. 389-394.
[7]   Jiang B. and Fei Y., Vehicle speed prediction by two-level data driven models in vehicular networks, IEEE Transactions on Intelligent Transportation, vol. 18, no. 7, pp. 1793-1801, 2017.
[8]   Park J., Murphey Y. L., McGee R., Kristinsson J. G., Kuang M. L., and Phillips A. M., Intelligent trip modeling for the prediction of an origin-destination traveling speed profile, IEEE Transactions on Intelligent Transportation, vol. 15, no. 3, pp. 1039-1053, 2014.
[9]   Yan M., Li M., He H., and Peng J., Deep learning for vehicle speed prediction, Energy Procedia, vol. 152, pp. 618-623, 2018.
[10]   Ma X., Dai Z., He Z., Ma J., Wang Y., and Wang Y., Learning traffic as images: A deep convolutional neural network for large-scale transportation network speed prediction, Sensors, vol. 17, no. 4, p. 818, 2017.
[11]   Zhang J., Wang F., Wang K., Lin W., Xu X., and Chen C., Data-driven intelligent transportation systems: A survey, IEEE Transactions on Intelligent Transportation, vol. 12, no. 4, pp. 1624-1639, 2011.
[12]   Gong Q., Li Y., and Peng Z.-R., Trip-based optimal power management of plug-in hybrid electric vehicles using gas-kinetic traffic flow model, presented at American Control Conference, Seattle, WA, USA, 2008.
[13]   Nait-Sidi-Moh A., Ruzmetov A., Bakhouya M., Naitmalek Y., and Gaber J., A prediction model of electric vehicle charging requests, in Proc. 9th Int. Conf. on Emerging Ubiquitous Systems and Pervasive Networks, Leuven, Belgium, 2018, pp. 127-134.
[14]   Xu T., Sun X., Wu Y., He Y., and Xie C., Artificial neural network and wavelet analysis application in speed forecast of Beijing urban freeway, in Proc. of IEEE Intelligent Vehicles Symposium, Xi’an, China, 2009, pp. 1004-1008.
[15]   Chen Y.-L., Huang C. H., Kuo Y.-W., and Wang S.-S., Artificial neural network for predictions of vehicle drivable range and period, presented at IEEE Int. Conf. on Vehicular Electronics and Safety, Istanbul, Turkey, 2012, pp. 329-333.
[16]   Yang J., Chou L., Tung C., Huang S., and Wang T., Average-speed forecast and adjustment via VANETs, Trans. on Vehicular Technology, vol. 62, no. 9, pp. 4318-4327, 2013.
[17]   Liu R., Xu S., Park J., Murphey Y. L., Kristinsson J., McGee R., Kuang M., and Phillips T., Real time vehicle speed prediction using gas-kinetic traffic modeling, in Proc. IEEE Symposium on Computational Intelligence in Vehicles and Transportation Systems, Paris, France, 2011, pp. 80-86.
[18]   Wang J., Gu Q., Wu J., Liu G., and Xiong Z., Traffic speed prediction and congestion source exploration: A deep learning method, in Proc. IEEE 16th Int. Conf. Data Mining (ICDM), Barcelona, Spain, 2016, pp. 499-508.
[19]   Liu H., Travel time prediction for urban networks, PhD dissertation, The Netherlands TRAIL Research School, Delft, The Netherlands, 2008.
[20]   Protzmann R., Schünemann B., and Radusch I., Simulation of convergent networks for intelligent transport systems with VSimRTI, in Networking Simulation for Intelligent Transportation Systems: High Mobile Wireless Nodes. Hoboken, NJ, USA: John Wiley & Sons, 2017, pp. 1-28.
[21]   Lopez A. P., Behrisch M., Bieker-Walz L., Erdmann J., Fl?tter?d Y. P., Hilbrich R., Lücken L., Rummel J., Wagner P., and Wiessner E., Microscopic traffic simulation using SUMO, presented at the IEEE Intelligent Transportation Systems Conf., Maui, HI, USA, 2018.
[22]   Lamghari H., Tajer A., Nait-Sidi-Moh A., and Dakkak B., An SUMO-based simulation for adaptive control of urban signalized intersection using petri nets, presented at the 4th World Conf. on Complex Systems, Ouarzazate, Maroc, 2019.
[23]   Hochreiter S. and Schmidhuber J., Long short-term memory, Neural Computation, vol. 9, no. 8, pp. 1735-1780, 1997.
[24]   Salah B., Ali F., Ali O., and Mohamed S., Optimal deep learning LSTM model for electric load forecasting using feature selection and genetic algorithm: Comparison with machine learning approaches, Energies, vol. 11, no. 7, p. 1636, 2018.
[25]   Krauss S., Wagner P., and Gawron C., Metastable states in a microscopic model of traffic flow, Physical Review E, vol. 55, no. 5, pp. 55-97, 1997.
[1] Wei Zhong, Ning Yu, Chunyu Ai. Applying Big Data Based Deep Learning System to Intrusion Detection[J]. Big Data Mining and Analytics, 2020, 3(3): 181-195.
[2] Sunitha Basodi, Chunyan Ji, Haiping Zhang, Yi Pan. Gradient Amplification: An Efficient Way to Train Deep Neural Networks[J]. Big Data Mining and Analytics, 2020, 3(3): 196-207.
[3] Chaity Banerjee, Tathagata Mukherjee, Eduardo Pasiliao Jr.. Feature Representations Using the Reflected Rectified Linear Unit (RReLU) Activation[J]. Big Data Mining and Analytics, 2020, 3(2): 102-120.
[4] Zhenxing Guo, Shihua Zhang. Sparse Deep Nonnegative Matrix Factorization[J]. Big Data Mining and Analytics, 2020, 03(01): 13-28.
[5] Qile Zhu, Xiyao Ma, Xiaolin Li. Statistical Learning for Semantic Parsing: A Survey[J]. Big Data Mining and Analytics, 2019, 2(4): 217-239.
[6] Ying Yu, Min Li, Liangliang Liu, Yaohang Li, Jianxin Wang. Clinical Big Data and Deep Learning: Applications, Challenges, and Future Outlooks[J]. Big Data Mining and Analytics, 2019, 2(4): 288-305.
[7] Wenmao Wu, Zhizhou Yu, Jieyue He. A Semi-Supervised Deep Network Embedding Approach Based on the Neighborhood Structure[J]. Big Data Mining and Analytics, 2019, 2(3): 205-216.
[8] Jiangcheng Zhu, Shuang Hu, Rossella Arcucci, Chao Xu, Jihong Zhu, Yi-ke Guo. Model Error Correction in Data Assimilation by Integrating Neural Networks[J]. Big Data Mining and Analytics, 2019, 2(2): 83-91.
[9] Jin Liu, Yi Pan, Min Li, Ziyue Chen, Lu Tang, Chengqian Lu, Jianxin Wang. Applications of Deep Learning to MRI Images: A Survey[J]. Big Data Mining and Analytics, 2018, 1(1): 1-18.
[10] Ning Yu, Zhihua Li, Zeng Yu. Survey on Encoding Schemes for Genomic Data Representation and Feature Learning—From Signal Processing to Machine Learning[J]. Big Data Mining and Analytics, 2018, 01(03): 191-210.
[11] Qianyu Meng, Kun Wang, Xiaoming He, Minyi Guo. QoE-Driven Big Data Management in Pervasive Edge Computing Environment[J]. Big Data Mining and Analytics, 2018, 01(03): 222-233.